M Ginn, A Palmer - arXiv preprint arXiv:2311.02777, 2023 - arxiv.org
Generalization is of particular importance in resource-constrained settings, where the available training data may represent only a small fraction of the distribution of possible …
Large Language Models (LLMs) have become capable of generating highly fluent text in certain languages, without modules specially designed to capture grammar or semantic …
BFP Dossou, I Houndayi, P Zantou… - arXiv preprint arXiv …, 2023 - arxiv.org
The Fon language, spoken by an average 2 million of people, is a truly low-resourced African language, with a limited online presence, and existing datasets (just to name but a …
P Rybak - arXiv preprint arXiv:2402.14408, 2024 - arxiv.org
Pre-trained language models have revolutionized the natural language understanding landscape, most notably BERT (Bidirectional Encoder Representations from Transformers) …
M Ginn - arXiv preprint arXiv:2303.14234, 2023 - arxiv.org
Language documentation is a critical aspect of language preservation, often including the creation of Interlinear Glossed Text (IGT). Creating IGT is time-consuming and tedious, and …
Recently, many Deep Learning fuzzers have been proposed for testing of DL libraries. However, they either perform unguided input generation (eg, not considering the …
D Nikolaev, J Grotenhuis, H Harel… - arXiv preprint arXiv …, 2024 - arxiv.org
The complex Ancient Egyptian (AE) writing system was characterised by widespread use of graphemic classifiers (determinatives): silent (unpronounced) hieroglyphic signs clarifying …
Abstract Language technology development is crucial for many downstream applications such as machine translation and language understanding. The lack of linguistic resources …
Since the publication of BERT in 2018, pretrained Transformer language models (TLMs) have been a foundational requirement for almost all natural language processing systems …